A Mean-Field-Game-Integrated MPC-QP Framework for Collision-Free Multi-Vehicle Control

In recent years, rapid progress in autonomous driving has been achieved through advances in sensing, control, and earning. However, as the complexity of traffic scenarios increases, ensuring safe interaction among vehicles remains a formidable challenge. Recent works combining artificial potential f...

Full description

Saved in:
Bibliographic Details
Main Authors: Liancheng Zheng, Xuemei Wang, Feng Li, Zebing Mao, Zhen Tian, Yanhong Peng, Fujiang Yuan, Chunhong Yuan
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Drones
Subjects:
Online Access:https://www.mdpi.com/2504-446X/9/5/375
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850258074123632640
author Liancheng Zheng
Xuemei Wang
Feng Li
Zebing Mao
Zhen Tian
Yanhong Peng
Fujiang Yuan
Chunhong Yuan
author_facet Liancheng Zheng
Xuemei Wang
Feng Li
Zebing Mao
Zhen Tian
Yanhong Peng
Fujiang Yuan
Chunhong Yuan
author_sort Liancheng Zheng
collection DOAJ
description In recent years, rapid progress in autonomous driving has been achieved through advances in sensing, control, and earning. However, as the complexity of traffic scenarios increases, ensuring safe interaction among vehicles remains a formidable challenge. Recent works combining artificial potential fields (APFs) with game-theoretic methods have shown promise in modeling vehicle interactions and avoiding collisions. However, these approaches often suffer from overly conservative decisions or fail to capture the nonlinear dynamics of real-world driving. To address these imitations, we propose a novel framework that integrates mean field game (MFG) theory with model predictive control (MPC) and quadratic programming (QP). Our approach everages the aggregate behavior of surrounding vehicles to predict interactive effects and embeds these predictions into an MPC-QP scheme for real-time control. Simulation results in complex driving scenarios demonstrate that our method achieves multiple autonomous driving tasks while ensuring collision-free operation. Furthermore, the proposed framework outperforms popular game-based benchmarks in terms of achieving driving tasks and producing fewer collisions.
format Article
id doaj-art-e3f07b1272ac49488340fd39f400ddf8
institution OA Journals
issn 2504-446X
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Drones
spelling doaj-art-e3f07b1272ac49488340fd39f400ddf82025-08-20T01:56:16ZengMDPI AGDrones2504-446X2025-05-019537510.3390/drones9050375A Mean-Field-Game-Integrated MPC-QP Framework for Collision-Free Multi-Vehicle ControlLiancheng Zheng0Xuemei Wang1Feng Li2Zebing Mao3Zhen Tian4Yanhong Peng5Fujiang Yuan6Chunhong Yuan7School of Mechanical Engineering, Shandong Huayu University of Technology, Dezhou 253034, ChinaSchool of Information Engineering, Shandong Huayu University of Technology, Dezhou 253034, ChinaSchool of Mechanical Engineering, Shandong Huayu University of Technology, Dezhou 253034, ChinaDepartment of Engineering Science and Mechanics, Shibaura Institute of Technology, 3-7-5 Toyosu, Koto-ku, Tokyo 135-8548, JapanJames Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UKCollege of Mechanical Engineering, Chongqing University of Technology, Chongqing 400054, ChinaCollege of Mechanical Engineering, Chongqing University of Technology, Chongqing 400054, ChinaLaboratory of Intelligent Home Appliances, Department of Artificial Intelligence, College of Science and Technology, Ningbo University, Ningbo 315300, ChinaIn recent years, rapid progress in autonomous driving has been achieved through advances in sensing, control, and earning. However, as the complexity of traffic scenarios increases, ensuring safe interaction among vehicles remains a formidable challenge. Recent works combining artificial potential fields (APFs) with game-theoretic methods have shown promise in modeling vehicle interactions and avoiding collisions. However, these approaches often suffer from overly conservative decisions or fail to capture the nonlinear dynamics of real-world driving. To address these imitations, we propose a novel framework that integrates mean field game (MFG) theory with model predictive control (MPC) and quadratic programming (QP). Our approach everages the aggregate behavior of surrounding vehicles to predict interactive effects and embeds these predictions into an MPC-QP scheme for real-time control. Simulation results in complex driving scenarios demonstrate that our method achieves multiple autonomous driving tasks while ensuring collision-free operation. Furthermore, the proposed framework outperforms popular game-based benchmarks in terms of achieving driving tasks and producing fewer collisions.https://www.mdpi.com/2504-446X/9/5/375autonomous vehicleinteractive drivingrisk potential fieldmodel predictive control
spellingShingle Liancheng Zheng
Xuemei Wang
Feng Li
Zebing Mao
Zhen Tian
Yanhong Peng
Fujiang Yuan
Chunhong Yuan
A Mean-Field-Game-Integrated MPC-QP Framework for Collision-Free Multi-Vehicle Control
Drones
autonomous vehicle
interactive driving
risk potential field
model predictive control
title A Mean-Field-Game-Integrated MPC-QP Framework for Collision-Free Multi-Vehicle Control
title_full A Mean-Field-Game-Integrated MPC-QP Framework for Collision-Free Multi-Vehicle Control
title_fullStr A Mean-Field-Game-Integrated MPC-QP Framework for Collision-Free Multi-Vehicle Control
title_full_unstemmed A Mean-Field-Game-Integrated MPC-QP Framework for Collision-Free Multi-Vehicle Control
title_short A Mean-Field-Game-Integrated MPC-QP Framework for Collision-Free Multi-Vehicle Control
title_sort mean field game integrated mpc qp framework for collision free multi vehicle control
topic autonomous vehicle
interactive driving
risk potential field
model predictive control
url https://www.mdpi.com/2504-446X/9/5/375
work_keys_str_mv AT lianchengzheng ameanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT xuemeiwang ameanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT fengli ameanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT zebingmao ameanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT zhentian ameanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT yanhongpeng ameanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT fujiangyuan ameanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT chunhongyuan ameanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT lianchengzheng meanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT xuemeiwang meanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT fengli meanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT zebingmao meanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT zhentian meanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT yanhongpeng meanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT fujiangyuan meanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol
AT chunhongyuan meanfieldgameintegratedmpcqpframeworkforcollisionfreemultivehiclecontrol